Related papers: PAD-Net: Multi-Tasks Guided Prediction-and-Distill…

In this work, we propose a single deep neural network for panoptic segmentation, for which the goal is to provide each individual pixel of an input image with a class label, as in semantic segmentation, as well as a unique identifier for…

Despite the fact that deep neural networks are powerful models and achieve appealing results on many tasks, they are too large to be deployed on edge devices like smartphones or embedded sensor nodes. There have been efforts to compress…

We propose a cross-modal attention distillation framework to train a dual-encoder model for vision-language understanding tasks, such as visual reasoning and visual question answering. Dual-encoder models have a faster inference speed than…

Nested named entity recognition (nested NER) is a fundamental task in natural language processing. Various span-based methods have been proposed to detect nested entities with span representations. However, span-based methods do not…

Previous knowledge distillation methods have shown their impressive performance on model compression tasks, however, it is hard to explain how the knowledge they transferred helps to improve the performance of the student network. In this…

Dataset distillation aims to minimize the time and memory needed for training deep networks on large datasets, by creating a small set of synthetic images that has a similar generalization performance to that of the full dataset. However,…

This paper addresses the problem of dense depth predictions from sparse distance sensor data and a single camera image on challenging weather conditions. This work explores the significance of different sensor modalities such as camera,…

Knowledge distillation facilitates the training of a compact student network by using a deep teacher one. While this has achieved great success in many tasks, it remains completely unstudied for image-based 6D object pose estimation. In…

Cross-view image translation is challenging because it involves images with drastically different views and severe deformation. In this paper, we propose a novel approach named Multi-Channel Attention SelectionGAN (SelectionGAN) that makes…

We propose a unified look at jointly learning multiple vision tasks and visual domains through universal representations, a single deep neural network. Learning multiple problems simultaneously involves minimizing a weighted sum of multiple…

Layer-wise distillation is a powerful tool to compress large models (i.e. teacher models) into small ones (i.e., student models). The student distills knowledge from the teacher by mimicking the hidden representations of the teacher at…

Convolutional Neural Networks (CNNs) are successfully used for the important automotive visual perception tasks including object recognition, motion and depth estimation, visual SLAM, etc. However, these tasks are typically independently…

We propose a deep learning-based channel estimation, quantization, feedback, and precoding method for downlink multiuser multiple-input and multiple-output systems. In the proposed system, channel estimation and quantization for limited…

A practical eye authentication (EA) system targeted for edge devices needs to perform authentication and be robust to presentation attacks, all while remaining compute and latency efficient. However, existing eye-based frameworks a) perform…

In image-assisted minimally invasive surgeries (MIS), understanding surgical scenes is vital for real-time feedback to surgeons, skill evaluation, and improving outcomes through collaborative human-robot procedures. Within this context, the…

Conventionally, image denoising and high-level vision tasks are handled separately in computer vision. In this paper, we cope with the two jointly and explore the mutual influence between them. First we propose a convolutional neural…

The prosperity of deep learning contributes to the rapid progress in scene text detection. Among all the methods with convolutional networks, segmentation-based ones have drawn extensive attention due to their superiority in detecting text…

In this paper, we introduce the concept of Prior Activation Distribution (PAD) as a versatile and general technique to capture the typical activation patterns of hidden layer units of a Deep Neural Network used for classification tasks. We…

Panoptic segmentation is a scene parsing task which unifies semantic segmentation and instance segmentation into one single task. However, the current state-of-the-art studies did not take too much concern on inference time. In this work,…

Multi-view representation learning aims to derive robust representations that are both view-consistent and view-specific from diverse data sources. This paper presents an in-depth analysis of existing approaches in this domain, highlighting…